CN110020150A - Information recommendation method and device - Google Patents
Information recommendation method and device Download PDFInfo
- Publication number
- CN110020150A CN110020150A CN201711243040.9A CN201711243040A CN110020150A CN 110020150 A CN110020150 A CN 110020150A CN 201711243040 A CN201711243040 A CN 201711243040A CN 110020150 A CN110020150 A CN 110020150A
- Authority
- CN
- China
- Prior art keywords
- information
- interest
- commercial circle
- attribute
- point name
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of information recommendation method and devices, wherein the information recommendation method includes: that server-side obtains information;The interest point name carried to the information identifies, obtains interest point name segment;Matching retrieval is carried out in the point of interest of storage according to the interest point name segment, obtains the point of interest that title and the interest point name segment match;The interest point name segment is obtained to match the commercial circle attribute of point of interest;The classification that the information is carried out according to the commercial circle attribute, the information recommendation of commercial circle where providing user by the information of classification.It solves the problems, such as that the information correlativity of recommendation information in the prior art is not high using information recommendation method provided by the present invention and device, and effectively improves the recommendation efficiency of information.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of information recommendation methods and device.
Background technique
With the development of internet technology, millions of information can be pushed to user by internet, for example,
When user strolls forum, the topic popular recently to user's recommendation, alternatively, recommending to user and being somebody's turn to do when user reads certain news
Information similar in news content when user goes window-shopping, recommends the commodity to enjoy great popularity to user, to facilitate user what is more
Obtain more information.
A kind of existing recommended method is the recommendation that carries out based on zoning where user, the recommended method be by with
The positioning in family geographical location is to judge zoning where user, and then the recommendation information of zoning recommends user where formation user.
For example, the city A user is pushed the relevant information in the city A.
However, often quantity is more and type is numerous and jumbled for the relevant information of zoning where user, the not only recommendation efficiency of information
It is lower, and it be easy to cause recommendation information and non-user is practical is concerned about, lack information correlativity.
Summary of the invention
In order to solve the above-mentioned technical problem, it is an object of the present invention to provide a kind of information recommendation method and devices.
Wherein, the technical scheme adopted by the invention is as follows:
A kind of information recommendation method, comprising: server-side obtains information;The interest point name carried to the information is known
Not, interest point name segment is obtained;Matching retrieval is carried out in the point of interest of storage according to the interest point name segment, is obtained
The point of interest that title and the interest point name segment match;The interest point name segment is obtained to match the quotient of point of interest
Enclose attribute;The classification that the information is carried out according to the commercial circle attribute, the letter of commercial circle where providing user by the information of classification
Breath is recommended.
A kind of information recommendation method, comprising: client carries out user's Geographic mapping, obtains location information;According to institute
It states location information and initiates information recommendation request to server-side;The server-side is received according to the commercial circle of commercial circle where indicating user
The information of attribute push, the property index value that the commercial circle attribute and the location information are converted to have index relative, institute
Information is stated to be sorted out in the server-side according to the commercial circle attribute.
A kind of information recommending apparatus, comprising: data obtaining module obtains information for server-side;Information identification module is used
It is identified in the interest point name carried to the information, obtains interest point name segment;Retrieval module is matched, basis is used for
The interest point name segment carries out matching retrieval in the point of interest of storage, obtains title and the interest point name segment phase
Matched point of interest;Attribute obtains module, matches the commercial circle attribute of point of interest for obtaining the interest point name segment;The
One information categorization module provides user by the information of classification for carrying out the classification of the information according to the commercial circle attribute
The information recommendation of place commercial circle.
A kind of information recommending apparatus, comprising: positioning initiation module carries out user's Geographic mapping for client, obtains
To location information;Initiation module is requested, for initiating information recommendation request to server-side according to the positional information;Information receives
Module, for receiving the information of commercial circle attribute push of the server-side according to commercial circle where indicating user, the commercial circle belongs to
Property the property index value that is converted to the location information there is index relative, the information is in the server-side according to institute
Commercial circle attribute is stated to be sorted out.
A kind of information recommending apparatus, including processor and memory are stored with computer-readable instruction on the memory,
The computer-readable instruction realizes information recommendation method as described above when being executed by the processor.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Information recommendation method as described above is realized when row.
In the above-mentioned technical solutions, identify to obtain interest point name segment by the interest point name that information carries, and according to
Interest point name segment carries out matching retrieval in the point of interest of storage, obtain title match with interest point name segment it is emerging
It is interesting, and then information is sorted out according to the commercial circle attribute of the point of interest, that is to say, that the information category of massive information is by root
It is believed that interest point name entrained by breath is classified as the commercial circle attribute of corresponding point of interest respectively, so that energy when information recommendation
It is enough to be recommended based on commercial circle where user indicated by the attribute of commercial circle, not only greatly reduce the quantity and kind of information to be recommended
Class is conducive to the recommendation efficiency for improving information, and recommendation results are that commercial circle where with user is closely related, are avoided with this
Recommendation information existing in the prior art lacks the problem of information correlativity.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
It can the limitation present invention.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and in specification together principle for explaining the present invention.
Fig. 1 is the schematic diagram of related implementation environment according to the present invention.
Fig. 2 is a kind of hardware block diagram of client shown according to an exemplary embodiment.
Fig. 3 is a kind of hardware block diagram of server-side shown according to an exemplary embodiment.
Fig. 4 is a kind of flow chart of information recommendation method shown according to an exemplary embodiment.
Fig. 5 be in Fig. 4 corresponding embodiment step 330 in the flow chart of one embodiment.
Fig. 6 be in Fig. 4 corresponding embodiment step 370 in the flow chart of one embodiment.
Fig. 7 is the flow chart of another information recommendation method shown according to an exemplary embodiment.
Fig. 8 is the flow chart of another information recommendation method shown according to an exemplary embodiment.
Fig. 9 is the flow chart of another information recommendation method shown according to an exemplary embodiment.
Figure 10 is the flow chart of another information recommendation method shown according to an exemplary embodiment.
Figure 11 is a kind of specific implementation schematic diagram of information recommendation method in an application scenarios.
Figure 12 is a kind of block diagram of information recommending apparatus shown according to an exemplary embodiment.
Figure 13 is that retrieval module is matched in Figure 12 corresponding embodiment in the block diagram of one embodiment.
Figure 14 is that attribute obtains module in the block diagram of one embodiment in Figure 12 corresponding embodiment.
Figure 15 is the block diagram of another information recommending apparatus shown according to an exemplary embodiment.
Figure 16 is the block diagram of another information recommending apparatus shown according to an exemplary embodiment.
Figure 17 is the block diagram of another information recommending apparatus shown according to an exemplary embodiment.
Figure 18 is a kind of block diagram of information recommending apparatus shown according to an exemplary embodiment.
Through the above attached drawings, it has been shown that the specific embodiment of the present invention will be hereinafter described in more detail, these attached drawings
It is not intended to limit the scope of the inventive concept in any manner with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate idea of the invention.
Specific embodiment
Here will the description is performed on the exemplary embodiment in detail, the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistented with the present invention.On the contrary, they be only with it is such as appended
The example of device and method being described in detail in claims, some aspects of the invention are consistent.
As previously described, because often quantity is more and type is numerous and jumbled for the relevant information of zoning where user, it is based on user institute
It is lower in the recommendation efficiency for the recommended method not only information that zoning is implemented, but also it be easy to cause recommendation information and non-user institute is practical
It is concerned about, lacks information correlativity.
As an example it is assumed that being mounted with the client with information recommendation function in terminal corresponding to user, then user borrows
Relevant information will be pushed by the client.No matter user is the area B for staying in the city A, or is worked in the area C in the city A,
Based on zoning where user, the i.e. city A, the relevant information in the city A is pushed to user always, recommendation at this time is then considered as lacking information
Correlation.
Under this explanation, zoning is also referred to as administrative region, for example, the city A belongs to zoning, the area B in the city A, the city A C
Area is also included in zoning scope.
For this purpose, spy of the present invention proposes a kind of information recommendation method, this kind of information recommendation method can effectively improve letter
The recommendation efficiency of breath, and be conducive to enhance the information correlativity of recommendation information.
Fig. 1 is a kind of schematic diagram of implementation environment involved in information recommendation method.The implementation environment includes two terminals
100 and server-side 200.
Wherein, terminal 100 corresponding to user can be desktop computer, laptop, tablet computer, smart phone or
Other have the function of the electronic equipment of information recommendation client, herein without limiting.Client with information recommendation function
It can be social category client, Domestic News class client, e-commerce client etc., the form of client, which can be, answers
With program class, it is also possible to web page class, is not limited herein.
By the network connection between terminal 100 and server-side 200, the client for running on terminal 100 will pass through use
Family Geographic mapping requests server-side 200 to carry out information recommendation.
For server-side 200, the interest point name carried based on information is carried out to the acquisition of point of interest commercial circle attribute,
To sort out according to the commercial circle attribute got to information, and then the request at customer in response end provides user place to client
The information recommendation service of commercial circle.
For the different user corresponding to the different terminals 100, due to the difference of commercial circle where user, will by according to
Commercial circle where family correspondingly pushes different information, has stronger information correlativity when ensure that information recommendation with this.
It is noted that server-side 200 can be a server, it is also possible to the service being made of multiple servers
Device cluster, or refer to cloud computing center.
For example, server-side 200 includes recommendation server and location server in an application scenarios, recommendation server is used
Commercial circle is carried out in user's Geographic mapping that client push information, location server is then used to be initiated according to client
The feedback of attribute, in order to which client carries out information recommendation according further to the commercial circle attribute request server-side 200.
In another application scene, recommendation server and location server are integrated into same server, and with this to visitor
Family end provides information recommendation service.
Referring to Fig. 2, Fig. 2 is a kind of block diagram of terminal shown according to an exemplary embodiment.
It should be noted that the terminal 100, which is one, adapts to example of the invention, it must not believe that there is provided to this
Any restrictions of the use scope of invention.The terminal 100 can not be construed to need to rely on or must have in Fig. 2 to show
Illustrative terminal 100 in one or more component.
As shown in Fig. 2, terminal 100 (only shows one including memory 101, storage control 103, one or more in Fig. 2
It is a) processor 105, Peripheral Interface 107, radio-frequency module 109, locating module 111, photographing module 113, audio-frequency module 115, touch-control
Screen 117 and key module 119.These components are mutually communicated by one or more communication bus/signal wire 121.
Wherein, memory 101 can be used for storing computer program and module, such as the letter in exemplary embodiment of the present
Computer-readable instruction corresponding to recommended method and device is ceased, processor 105 is by executing the meter being stored in memory 101
Calculation machine readable instruction completes information recommendation method to carry out various functions and data processing.
The carrier that memory 101 is stored as resource, can be random access memory, for example high speed random access memory, it is non-easily
The property lost memory, such as one or more magnetic storage devices, flash memory or other solid-state memories.Storage mode can be short
Temporary storage permanently stores.
Peripheral Interface 107 may include an at least wired or wireless network interface, at least one series-parallel translation interface, at least
One input/output interface and at least USB interface etc., for coupleeing memory 101 for external various input/output devices
And processor 105, to realize the communication with external various input/output devices.
Radio-frequency module 109 is used for transceiving electromagnetic wave, the mutual conversion of electromagnetic wave and electric signal is realized, to pass through communication network
Network is communicated with other equipment.Communication network includes cellular telephone networks, WLAN or Metropolitan Area Network (MAN), above-mentioned communication network
Various communication standards, agreement and technology can be used in network.
Locating module 111 is used to obtain the geographical location of terminal 100 being currently located.The example of locating module 111 includes
But it is not limited to GPS (GPS), the location technology based on WLAN or mobile radio communication.
Photographing module 113 is under the jurisdiction of camera, for shooting picture or video.The picture or video of shooting can be deposited
In storage to memory 101, host computer can also be sent to by radio-frequency module 109.
Audio-frequency module 115 provides a user audio interface, may include one or more microphone interfaces, one or more
Speaker interface and one or more earphone interfaces.The interaction of audio data is carried out by audio interface and other equipment.Sound
Frequency can also be sent according to can store to memory 101 by radio-frequency module 109.
Touch Screen 117 provides an I/O Interface between terminal 100 and user.Specifically, user can pass through
Touch Screen 117 carries out the gesture operations such as input operation, such as click, touch, sliding, so that terminal 100 operates the input
It is responded.Any one form of text, picture or video or combination are then formed by output content and passed through by terminal 100
Touch Screen 117 shows to user and exports.
Key module 119 includes at least one key, to provide user's interface inputted to terminal 100, user
Terminal 100 can be made to execute different functions by pressing different keys.For example, sound regulating key is for user's realization pair
The adjusting for the wave volume that terminal 100 plays.
It is appreciated that structure shown in Fig. 2 is only to illustrate, terminal 100 may also include more more or fewer than shown in Fig. 2
Component, or with the component different from shown in Fig. 2.Each component shown in Fig. 2 can use hardware, software or a combination thereof
To realize.For example, terminal 100 according to the present invention in addition to necessary data processing, input (for example, key, touch
Deng) and export except functions such as (for example, screen are shown), also have the function of to position and network etc..
Fig. 3 is a kind of hardware block diagram of server-side 200 shown according to an exemplary embodiment.It needs to illustrate
It is that the server-side 200 is one and adapts to example of the invention, must not believe that there is provided to use scope of the invention
Any restrictions.The server-side 200 can not be construed to need to rely on or must have shown in Fig. 3 illustratively to service
One or more component in end 200.
The hardware configuration of the server-side 200 can generate biggish difference due to the difference of configuration or performance, such as Fig. 3 institute
Show, server-side 200 include: power supply 210, interface 230, at least a memory 250 and an at least central processing unit (CPU,
Central Processing Units)270。
Wherein, power supply 210 is used to provide operating voltage for each hardware device in server-side 200.
Interface 230 includes an at least wired or wireless network interface 231, at least a string and translation interface 233, at least one defeated
Enter output interface 235 and at least USB interface 237 etc., is used for and external device communication.
The carrier that memory 250 is stored as resource, can be read-only memory, random access memory, disk or CD
Deng the resource stored thereon includes operating system 251, application program 253 and data 255 etc., and storage mode can be of short duration
It stores or permanently stores.Wherein, operating system 251 is for managing and controlling each hardware device in server-side 200 and answer
It can be Windows with program 253 to realize calculating and processing of the central processing unit 270 to mass data 255
ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..Application program 253 be based on operating system 251 it
The upper computer program for completing at least one particular job, may include an at least module (being not shown in Fig. 3), each module
The series of computation machine readable instruction to server-side 200 can be separately included.Data 255 can be stored in disk
Photo, picture etc..
Central processing unit 270 may include the processor of one or more or more, and be set as through bus and memory
250 communications, for the mass data 255 in operation and processing memory 250.
As described in detail above, memory will be read by central processing unit 270 by being applicable in server-side 200 of the invention
The form of the series of computation machine readable instruction stored in 250 completes information recommendation method.
In addition, also can equally realize the present invention by hardware circuit or hardware circuit combination software instruction, therefore, realize
The present invention is not limited to the combinations of any specific hardware circuit, software and the two.
Referring to Fig. 4, in one exemplary embodiment, a kind of information recommendation method is suitable for implementation environment shown in Fig. 1
The structure of server-side 200, the server-side 200 can be as shown in Figure 3.
This kind of information recommendation method can be executed by server-side 200, may comprise steps of:
Step 310, server-side obtains information.
Information can be text information, video information, merchandise news etc., and the present embodiment does not make the type of information specific
It limits.Different application scenarios can be corresponded to accordingly, due to the different type of information, are read for example, text information can correspond to news
Scene is read, video information can correspond to video-see scene, and merchandise news can correspond to shopping scene, and therefore, the present embodiment is provided
Information recommendation method can according to the different type of information be suitable for different application scenarios.
For server-side, information will be got by different information sources according to the different type of information.For example, literary
The various topics that this information can be issued in forum, video information can derive from the public platform of Domestic News class, commodity letter
Breath can the e-commerce platform etc. built of source Mr. Yu market.
After obtaining information, just it can be sorted out for information, to provide information recommendation service to client.
Step 330, the interest point name carried to information identifies, obtains interest point name segment.
Point of interest (POI, Point of Interest) is related with geographical location, can be used for terrestrial reference in map, sight spot etc.
Mark, in order to which server-side can provide a user location information service according to point of interest, for example, geographical location query service.
Point of interest includes but is not limited to title, classification, longitude, latitude, affiliated zoning, affiliated commercial circle etc..Correspondingly, interest point name
Segment then refers to the interest point name that information carries.
For example, a specific point of interest M is: entitled " restaurant M ", classification are " food and beverage sevice ", longitude is " X ", latitude
Degree is " Y ", affiliated zoning is " area the city A C ", affiliated commercial circle is " commercial circle Z ".Assuming that including interest point name " M meal in information
Shop ", then " restaurant M " is considered as interest point name segment.
Further, information includes but is not limited to information header, information content etc., and interest point name can be needle in identifying
Information header is carried out, is also possible to for the information content, can also be emerging to what is carried in information header and the information content
Interest point title is identified, is not limited herein.
For example, information is video information, which includes video title and video content, it is assumed that video title carries
Interesting point title " restaurant M ", then identify to obtain interest point name segment by the interest point name for carrying out the video title
For " restaurant M ".
Or information is merchandise news, which includes product name and commodity details, it is assumed that in commodity details
It describes the commodity and belongs to the food sold fast in the restaurant M, then the knowledge carried out by the interest point name for including to the commodity details
Not, it is " restaurant M " that interest point name segment, which can be obtained,.
Step 350, matching retrieval is carried out in the point of interest of storage according to interest point name segment, obtains title and interest
The point of interest that point name segment matches.
In server-side, it will be stored for the point of interest of magnanimity, so as to based on the point of interest mark carried out in map
It infuses and provides a user the services such as geographical location inquiry, positioning.
It is appreciated that it is different to store the point of interest title that is included in server-side, as a result, in order to obtain title with it is emerging
The point of interest that interest point name segment matches, then need the foundation using interest point name segment as matching retrieval.
For example, interest point name segment is " restaurant M ", then it, just can be by the point of interest of magnanimity by matching retrieval
Allot the point of interest M in entitled " restaurant M ".
Step 370, interest point name segment is obtained to match the commercial circle attribute of point of interest.
Commercial circle attribute is used to indicate some commercial circle, suitable for different application scenarios.For example, the commercial circle attribute of point of interest
It is then the instruction affiliated commercial circle of point of interest, and for a user, commercial circle attribute then indicates commercial circle where user.
For the commercial circle attribute of point of interest for characterizing the affiliated commercial circle of point of interest, the affiliated commercial circle of the point of interest can be only by the interest
Point composition, is also possible to also include other associated points of interest, not be limited herein.Wherein, it is associated and refers to it
His point of interest and the point of interest belong to same zoning, alternatively, other points of interest are within the scope of the point of interest periphery distance to a declared goal, again
Alternatively, other points of interest and the point of interest belong to same category and are located within the scope of the distance to a declared goal of periphery, for example, 500 meters.
It should be appreciated that point of interest can include belonging to commercial circle information, can also only indicate food and drink near it,
The relevant informations such as shopping.Therefore, it if point of interest has included affiliated commercial circle, can directly extract to obtain the commercial circle of point of interest
Attribute.
If point of interest do not include belonging to commercial circle information, can according to indicated by it near food and drink, shopping etc.
It further refines to obtain commercial circle attribute in relevant information.For example, point of interest indicates that it nearby has " restaurant M ", and " restaurant M " is located at
The commercial circle Z, " commercial circle Z " is considered as the commercial circle attribute of the point of interest as a result,.
Certainly, in other embodiments, commercial circle attribute can also be carried out for point of interest and other associated points of interest
It is pre-configured with, correspondingly, the commercial circle attribute of point of interest and other associated points of interest is the commercial circle attribute of configuration.
For example, point of interest J and point of interest K does not include the information of affiliated commercial circle, since the classification of the two belongs to " meal
Drink-service business ", and within the scope of 500 meters of the periphery in " restaurant M ", then commercial circle Z where being pre-configured with " restaurant M " as point of interest J with
The commercial circle attribute of point of interest K, when carrying out the acquisition of point of interest commercial circle attribute as a result, the commercial circle attribute of point of interest J and point of interest K are
For " commercial circle Z ".
Step 390, the classification that information is carried out according to commercial circle attribute, the letter of commercial circle where providing user by the information of classification
Breath is recommended.
After getting the commercial circle attribute of point of interest, just information can be sorted out based on the commercial circle attribute, i.e., with
Commercial circle attribute is as the information category for being classified information.
For a user, commercial circle attribute indicates commercial circle where user, as a result, when client passes through user geographical location
When positioning and initiating to request to server-side, server-side just can carry out information recommendation according to the user geographical location navigated to.
For example, user geographical location indicates that user is located in the commercial circle Z, correspondingly, server-side will be " Z according to commercial circle attribute
Commercial circle " to user's pushed information classification be " commercial circle Z " information.Wherein, information category is that the information of " commercial circle Z " can refer to hair
If the raw Domestic News in " commercial circle Z ", can also refer to the commodity in " commercial circle Z " hot buy, or heat is chatted in " commercial circle Z "
Topic etc..
By process as described above, the localization for realizing information is sorted out, so that the information based on commercial circle attribute
Recommending can be closely related with commercial circle where user, with this enhancement information correlation.
In addition, commercial circle where the value volume and range of product of information to be recommended zoning where user is contracted to user, subtracts significantly
The value volume and range of product for having lacked information to be recommended is conducive to the recommendation efficiency for improving information.
Referring to Fig. 5, in one exemplary embodiment, step 330 may comprise steps of:
Step 331, interest point name matching is carried out according to interest point name dictionary in the information, obtains calling the roll comprising interest
At least text fragments claimed.
Interest point name dictionary, it can be understood as it is the set of the title of magnanimity point of interest, interest point name as a result,
Match, be then that interest point name entrained by the title and information by magnanimity point of interest compares, is obtained with this comprising point of interest
The text fragments of title.
It is appreciated that the possible more than one of interest point name entrained by information, therefore, the text comprising interest point name
The quantity of segment is at least one.
Further, in interest point name matching, text fragments comprising interest in addition to will also call the roll comprising interest point name
The preceding suffix information claimed.
For example, including " the Emperor Qin Huairou four seas " in information, then the text fragments matched comprising interest in addition to calling the roll
Claim " Huairou ", also by comprising the word adjacent with the interest point name, i.e., before suffix information " Emperor Qin ", " four seas ".
After obtaining text fragments, the foundation that just can be identified in this, as interest point name passes through interest point name
And its semantic relation between preceding suffix information effectively ensures the precision of subsequent interest point name identification.
Step 333, relevance ranking is carried out to the interest point name in an at least text fragments.
Due to the text fragments comprising interest point name quantity may there are two or more, in order to improve interest point name
The efficiency of identification, and then guarantee the precision of interest point name identification, it will be for the point of interest in two or more text fragments
Title carries out relevance ranking, to obtain the included highest text fragments of interest point name correlation, and is directed to this article this film
The subsequent interest point name identification of Duan Jinhang.
For example, the interest point name that a text fragments include is " Beijing East 2nd Ring Road ", another text fragments includes
Interest point name is " Oriental Pearl's tower ", it is seen then that the correlation of above-mentioned two interest point name is very low.Assuming that there are one texts
The interest point name that segment includes is " Shanghai Lujiazui ", at this point, interest point name " Oriental Pearl's tower " and interest point name " on
Extra large Lujiazui " is considered as that correlation is higher, then carry out interest point name identification will not be include interest point name " Beijing east two
The text fragments of ring ".For interest point name " Oriental Pearl's tower " and interest point name " Shanghai Lujiazui ", by further
Correlation calculations will obtain the highest interest point name of correlation, and obtain included interest point name correlation highest with this
Text fragments.
For example, the correlation of the interest point name carried in information header, which is lower than in the information content, to be carried in correlation calculations
Interest point name, interest point name be a certain specific landscape correlation be higher than interest point name be a certain zoning.
By above-mentioned realization process, text fragments corresponding to the highest interest point name of correlation can carry out interest
The identification of point title not only contributes to reduction system processing task amount, improves system treatment effeciency, and advantageously ensure that interest
The precision of point title identification.
Step 335, the included highest text fragments of interest point name correlation are identified using Named Entity Extraction Model,
Obtain interest point name segment.
Assuming that the highest interest point name of correlation is " Oriental Pearl's tower ", then corresponds to text fragments and know by name entity
The interest point name segment that other model identifies is " Oriental Pearl's tower ".
Wherein, Named Entity Extraction Model is obtained according to suffix information training before point of interest and/or geographical location.
Specifically, by obtain magnanimity point of interest and/or geographical location before suffix information (for example, being located at, place, big
Tall building, Technology Park etc.) it is used as training data, and mark and to form trained set, name Entity recognition network, Jin Erli are constructed with this
It is named the training of entity recognition model with neural network model, thus obtains Named Entity Extraction Model.
In above process, the generation of word in identification process, word, sentence, and benefit are enhanced using the point of interest of magnanimity
Sew the semanteme in information refinement identification process between interest point name and its preceding suffix information with the relevant front and back in geographical location
Relationship, so as to improve the precision of interest point name identification.
Further, in training, Named Entity Extraction Model can also be carried out using the methods of semi-supervised learning progressive
The training of formula further improves the precision of interest point name identification with this.
It is illustrated by taking the text fragments in " the Emperor Qin Huairou four seas " as an example, letter is sewed with interest point name " Huairou ", front and back
The input of " Emperor Qin " and " four seas " as Named Entity Extraction Model is ceased, before and after magnanimity point of interest and/or geographical location
Sew name Entity recognition network constructed by information, i.e. confirmation text segment does not carry interest point name, eliminates with this
There are the interest point name of ambiguity and its preceding suffix informations for semantic relation.
Under the action of above-described embodiment, the precision of point of interest identification is effectively improved, ensure that interest point name piece
The accuracy of section is conducive to ensure the accuracy that subsequent point of interest commercial circle attribute obtains, and then improves the precision of information recommendation.
Referring to Fig. 6, in one exemplary embodiment, point of interest does not include the information of affiliated commercial circle, commercial circle attribute
Acquisition process be pre-configured with it is related.
Correspondingly, step 370 may comprise steps of:
Step 371, matched by interest point name segment and extract location information in point of interest, and the position extracted is believed
Breath is converted to property index value.
As previously mentioned, point of interest includes but is not limited to title, classification, longitude, latitude, affiliated zoning, affiliated commercial circle etc..
Therefore, longitude, latitude, affiliated zoning can include but is not limited to by the location information extracted in point of interest.
Property index value and commercial circle attribute have index relative, are used to uniquely identify commercial circle.That is, a quotient
Enclose the corresponding property index value in commercial circle indicated by attribute.For example, commercial circle attribute is " commercial circle Z ", corresponding property index value
It is 1, by the index relative between property index value and commercial circle attribute, commercial circle attribute just can be indexed by property index value 1
For " commercial circle Z ".
As shown in fig. 7, in an embodiment in the specific implementation, index relative between property index value and commercial circle attribute
Building process may comprise steps of:
Step 410, region unit division is carried out to the affiliated zoning of the point of interest of storage according to specified region unit parameter, to divide
Obtained region unit configuration attribute index value.
Step 430, commercial circle attribute configuration is carried out to region unit according to the point of interest in region unit.
Step 450, the index relative between property index value and commercial circle attribute is constructed.
It is appreciated that the point of interest of storage is magnanimity, then the affiliated zoning of magnanimity point of interest then may be entire China, or
The entire Asia of person.For this purpose, in order to improve the information correlativity of recommendation information, it, will be right also for the recommendation efficiency for improving information
The affiliated zoning of magnanimity point of interest is finely divided.
Specifically, specified region unit parameter can be region number of blocks, region block size can also be, for example, 100 meters
× 100 meters, herein without limiting.
Region unit division is carried out according to specified region unit parameter, the affiliated zoning of magnanimity point of interest is divided into multiple regions
Block, and the configuration of property index value is carried out for multiple regions block.More preferably, according to the geographical location relationship between each region unit, according to
Dispose to sequence property index value.
Due to magnanimity point of interest random distribution, region unit may include one and the above point of interest, be also possible to not
Include point of interest.
For the region unit comprising point of interest, commercial circle will be carried out according to the classification of point of interest, affiliated commercial circle etc. in region unit
The configuration of attribute.For example, the property index value that certain region unit is configured is 1, point of interest M is contained in the region unit, point of interest M
Affiliated commercial circle be " commercial circle Z ", then the commercial circle attribute that the region unit is configured be " commercial circle Z ", and with this construct property index value 1 with
Index relative between commercial circle attribute " commercial circle Z ".Correspondingly, the commercial circle attribute for being under the jurisdiction of other points of interest of the region unit also regards
For " commercial circle Z ".
After completing the configuration of property index value and commercial circle attribute, the point of interest in region unit all has corresponding attribute
Index value and commercial circle attribute just can index to obtain quotient after learning point of interest based on this according to corresponding property index value
Enclose attribute.
Further, for the region unit for not including point of interest, attribute will be drawn according to zoning configuring area where region unit, and
The index relative between property index value and zoning attribute is constructed with this.Wherein, zoning attribute indicates some zoning.
That is, property index value is equipped with for each region unit, for the region unit comprising point of interest
For, it is configured for commercial circle attribute, and for the region unit for not including point of interest, then it is configured with zoning attribute, is based on structure as a result,
The index relative built, property index value or index obtain commercial circle attribute or index obtains zoning attribute, and then just can be with
This is the information according to commercial circle where recommending it to user, alternatively, the information of zoning where it.
Step 373, commercial circle attribute is obtained according to the index relative between property index value and commercial circle attribute.
In this process, the point of interest of magnanimity is configured for commercial circle attribute, provides sufficient foundation for follow-up classification,
It ensure that information recommendation can be carried out based on commercial circle attribute with this, thus information correlativity when enhancement information is recommended.
Referring to Fig. 8, in one exemplary embodiment, after step 390, method as described above may include following step
It is rapid:
Step 510, client is received to request by the information recommendation that user's Geographic mapping is initiated.
Step 530, according to information recommendation request in location information be converted to property index value.
Step 550, the commercial circle attribute that there is index relative with property index value is obtained, is to client push information category
The information of obtained commercial circle attribute.
Location information in information recommendation request, is different from the location information extracted in point of interest, is to pass through user
What Geographic mapping obtained, it is used to indicate user geographic location.
Conversion, is the longitude and latitude boundary by region unit compared with the longitude and latitude that user geographic location indicates.If with
The longitude and latitude of family geographic location instruction is then considered as user and is located at some region in the longitude and latitude boundary of some region unit
In block, correspondingly, indicate that the location information in user geographical location is converted into the property index value of some region unit.
As previously described, because region unit can not include point of interest, can also include one and the above point of interest, therefore,
Region unit can be configured zoning attribute, be also possible to be configured with commercial circle attribute.
Assuming that the region unit where user includes point of interest, then it is considered as user and is located at some commercial circle, then according to region unit institute
The information of commercial circle where the commercial circle attribute of configuration pushes user to user.
Assuming that the region unit where user does not include point of interest, then it is considered as user and is located at some zoning, then according to region unit
The information of zoning where the zoning attribute configured pushes user to user.
In above process, the localization for realizing information is recommended, information when effectively enhancing information recommendation with this
Correlation.
Referring to Fig. 9, in one exemplary embodiment, method as described above can with the following steps are included:
Step 610, when unidentified to interest point name segment, information source belonging to confirmation message.
Step 630, information is sorted out according to the zoning attribute in information source, to provide the information of user place zoning
Recommend.
It is appreciated that due to and not all information all carry point of interest, interest point name identification is carried out to information
When, it is possible to it is unable to get interest point name segment.
For this purpose, the information for not carrying point of interest will be sorted out according to the zoning attribute in information source in the present embodiment, into
And the information by sorting out provides the information recommendation of zoning where user.
Wherein, zoning attribute is used to indicate some zoning, suitable for different application scenarios.For example, the area in information source
Drawing attribute then is the instruction affiliated zoning in information source, and for a user, zoning attribute then indicates zoning where user.
As previously mentioned, the various topics that information source can issue in forum, can also derive from Domestic News
Class public platform, the e-commerce platform etc. that can be built with source Mr. Yu market.Correspondingly, the zoning attribute in information source
Used geographical location when can refer to forum, public platform registration, is also possible to certain market geographic location, can also be by
Forum, public platform.
In an embodiment in the specific implementation, the acquisition process of the zoning attribute in information source may comprise steps of:
Commercial circle attribute or zoning attribute when according to information categorization carry out zoning distribution statistics to information source, obtain letter
Cease the zoning attribute in source.
For example, information a and information b belong to same information source, commercial circle attribute when information a sorts out is " commercial circle Z ", the Z
Commercial circle is located at the area the city A C, therefore, when the information source of the information carries out zoning distribution statistics, the zoning attribute in the information source
The probability for being configured as " area the city A C " increases.
Zoning attribute when information b sorts out is " area the city A B ", so that the zoning attribute in the information source is configured
Probability for " area the city A B " increases, and due to all referring to the city A with information a, then it further increases zoning attribute and is configured as
The probability in " city A ".
After the massive information from the information source is sorted out, it will be come using the highest zoning of probability as information
The zoning attribute in source.
It is noted that when carrying out information categorization, information otherwise by the point of interest of carrying according to commercial circle attribute
Sort out or sorted out due to not carrying point of interest according to zoning attribute, in other words, same information is come
It says, information category is the one of which in commercial circle attribute or zoning attribute, and then the information as commercial circle where user pushes away
User is given, alternatively, the information as zoning where user is pushed to user.
Cooperation through the foregoing embodiment, information can not only be sorted out according to the commercial circle attribute of point of interest, can be with
Sorted out according to the zoning attribute in information source, improve the versatility of information recommendation, there is very strong practicability.
Referring to Fig. 10, in one exemplary embodiment, a kind of information recommendation method is suitable for implementation environment shown in Fig. 1
The structure of terminal 100, the terminal 100 can be as shown in Figure 2.
This kind of information recommendation method can be by, with the client executing of information recommendation function, may include in terminal 100
Following steps:
Step 710, client carries out user's Geographic mapping, obtains location information.
Step 730, information recommendation request is initiated to server-side according to location information.
Step 750, the information of commercial circle attribute push of the server-side according to commercial circle where indicating user is received.
Wherein, the property index value that commercial circle attribute and location information are converted to has index relative, and information is in server-side
In sorted out according to commercial circle attribute.
Figure 11 is the specific implementation schematic diagram according to information recommendation method a kind of in an application scenarios.This kind of information recommendation side
Method is suitable for different application scenarios, is now illustrated for different application scenarios to this kind of information recommendation method.
In an application scenarios, the client with information recommendation function is Domestic News class client, then recommendation service
Device provides text information recommendation service to client.Correspondingly, commercial circle attribute and zoning attribute indicate the generation of Domestic News
Ground.
When client initiates user's Geographic mapping to location server, location server will be according to user location
Position is managed to the corresponding attribute of client feedback.For example, user is located at some commercial circle, then commercial circle attribute is fed back, alternatively, user position
In some zoning, then zoning attribute is fed back.
Further, client just carries out text information recommendation according to the feedback request recommendation server of location server.
For recommendation server, text information is sorted out according to commercial circle attribute or zoning attribute in advance, i.e. text information
Information category be commercial circle attribute or zoning attribute, be based on this, recommendation server will be recommended corresponding according to the request of client
The text information of information category.
For example, the Domestic News occurred in some commercial circle are pushed when user is located at some commercial circle, whereas if
User is not in any commercial circle, then pushes the Domestic News occurred in the zoning to user according to zoning where user.
Hereby it is achieved that the localization of Domestic News is recommended, with the variation of user geographic location, recommendation information
It will change therewith, so that user grasps the Domestic News that periphery is occurred in real time, information correlativity is effectively enhanced with this.
In another application scene, the client with information recommendation function is e-commerce client, then recommends to take
Business device provides the service of commodity information recommendation to client.Correspondingly, commercial circle attribute and zoning attribute indicate the market of commodity.
For example, the commodity sold in some commercial circle are pushed, whereas if user when user is located at some commercial circle
It is not in any commercial circle, then pushes the commodity sold in the zoning to user according to zoning where user.
Hereby it is achieved that the localization of commodity is recommended, user can grasp the commodity that periphery is sold in real time, improve
The accuracy of commercial product recommending.
Following is apparatus of the present invention embodiment, can be used for executing information recommendation method according to the present invention.For this
Undisclosed details in invention device embodiment please refers to information recommendation method embodiment according to the present invention.
Figure 12 is please referred to, in one exemplary embodiment, a kind of information recommending apparatus 900 includes but is not limited to: information obtains
Modulus block 910, information identification module 930, matching retrieval module 950, attribute obtain module 970 and first information classifying module
990。
Wherein, data obtaining module 910 obtains information for server-side.
The interest point name that information identification module 930 is used to carry information identifies, obtains interest point name segment.
Matching retrieval module 950 is used to carry out matching retrieval in the point of interest of storage according to interest point name segment, obtains
The point of interest to match to title and interest point name segment.
Attribute, which obtains module 970 and is used to obtain interest point name segment, to match the commercial circle attribute of point of interest.
First information classifying module 990 is used to carry out the classification of information according to commercial circle attribute, is provided by the information of classification
The information recommendation of commercial circle where user.
Figure 13 is please referred to, in one exemplary embodiment, information identification module 930 includes but is not limited to: name-matches list
Member 931, sequencing unit 933 and recognition unit 935.
Wherein, name-matches unit 931 is used to carry out interest point name matching in the information according to interest point name dictionary,
Obtain at least text fragments comprising interest point name.
Sequencing unit 933 is used to carry out relevance ranking to the interest point name in an at least text fragments.
Recognition unit 935 is used to identify the included highest text of interest point name correlation using Named Entity Extraction Model
This segment, obtains interest point name segment, and Named Entity Extraction Model is according to suffix information before point of interest and/or geographical location
What training obtained.
Figure 14 is please referred to, in one exemplary embodiment, attribute obtains module 970 and includes but is not limited to: position conversion is single
Member 971 and property index unit 973.
Wherein, position converting unit 971, which is used to be matched by interest point name segment, extracts location information in point of interest, and
The location information extracted is converted into property index value.
Property index unit 973 is used to obtain commercial circle according to the index relative between property index value and commercial circle attribute to belong to
Property.
Figure 15 is please referred to, in one exemplary embodiment, device 900 as described above further includes but is not limited to: index value
Configuration module 1010, attribute configuration module 1030 and relationship construct module 1050.
Wherein, index value configuration module 1010 be used for according to specified region unit parameter to the affiliated zoning of the point of interest of storage into
Row region unit divides, to divide obtained region unit configuration attribute index value.
Attribute configuration module 1030 is used to carry out commercial circle attribute configuration to region unit according to the point of interest in region unit.
Relationship building module 1050 is used to construct the index relative between property index value and commercial circle attribute.
Please refer to Figure 16, in one exemplary embodiment, device 900 as described above further includes but is not limited to: request connects
Receive module 1110, location conversion module 1130 and info push module 1150.
Wherein, request receiving module 1110 is for receiving the information recommendation that client is initiated by user's Geographic mapping
Request.
Location information of the location conversion module 1130 in being requested according to information recommendation is converted to property index value.
Info push module 1150 is used to obtain the commercial circle attribute for having index relative with property index value, pushes away to client
Send information category by acquisition commercial circle attribute information.
Figure 17 is please referred to, in one exemplary embodiment, device 900 as described above further includes but is not limited to: obtaining in source
Modulus block 1210 and the second information categorization module 1230.
Wherein, when source obtains module 1210 and is used for when unidentified to interest point name segment, letter belonging to confirmation message
Cease source.
Second information categorization module 1230 is for sorting out information according to the zoning attribute in information source, to provide use
The information recommendation of zoning where family.
In one exemplary embodiment, device 900 as described above further includes but is not limited to: zoning statistical module.
Wherein, zoning statistical module for according to information categorization when commercial circle attribute or zoning attribute to information source into
Row zoning distribution statistics obtain the zoning attribute in information source
Figure 18 is please referred to, in one exemplary embodiment, a kind of information recommending apparatus 1300 includes but is not limited to: positioning hair
Play module 1310, request initiation module 1330 and information receiving module 1350.
Wherein, positioning initiation module 1310 carries out user's Geographic mapping for client, obtains location information.
Initiation module 1330 is requested to be used to initiate information recommendation request to server-side according to location information.
Information receiving module 1350 is used to receive commercial circle attribute push of the server-side according to commercial circle where indicating user
The property index value that information, commercial circle attribute and location information are converted to has index relative, and information is in server-side according to quotient
Circle attribute is sorted out.
It should be noted that information recommending apparatus provided by above-described embodiment is when carrying out invitation processing, only with
The division progress of above-mentioned each functional module can according to need and for example, in practical application by above-mentioned function distribution by not
Same functional module is completed, i.e., the internal structure of information recommending apparatus will be divided into different functional modules, to complete above retouch
The all or part of function of stating.
In addition, the embodiment of information recommending apparatus and information recommendation method provided by above-described embodiment belongs to same structure
Think, the concrete mode that wherein modules execute operation is described in detail in embodiment of the method, no longer superfluous herein
It states.
In one exemplary embodiment, a kind of information recommending apparatus, including processor and memory.
Wherein, it is stored with computer-readable instruction on memory, realization when which is executed by processor
Information recommendation method in the various embodiments described above.
In one exemplary embodiment, a kind of computer readable storage medium, is stored thereon with computer program, the calculating
The information recommendation method in the various embodiments described above is realized when machine program is executed by processor.
Above content, preferable examples embodiment only of the invention, is not intended to limit embodiment of the present invention, this
Field those of ordinary skill central scope according to the present invention and spirit can be carried out very easily corresponding flexible or repaired
Change, therefore protection scope of the present invention should be subject to protection scope required by claims.
Claims (12)
1. a kind of information recommendation method characterized by comprising
Server-side obtains information;
The interest point name carried to the information identifies, obtains interest point name segment;
Matching retrieval is carried out in the point of interest of storage according to the interest point name segment, obtains title and the interest is called the roll
The point of interest for claiming segment to match;
The interest point name segment is obtained to match the commercial circle attribute of point of interest;
The classification that the information is carried out according to the commercial circle attribute, the information of commercial circle pushes away where providing user by the information of classification
It recommends.
2. the method as described in claim 1, which is characterized in that the interest point name carried to the information is known
Not, interest point name segment is obtained, comprising:
Interest point name matching is carried out in the information according to interest point name dictionary, is obtained comprising interest point name at least
One text fragments;
Relevance ranking is carried out to the interest point name in an at least text fragments;
The included highest text fragments of interest point name correlation are identified using Named Entity Extraction Model, obtain the interest
Point name segment, the Named Entity Extraction Model are obtained according to suffix information training before point of interest and/or geographical location.
3. the method as described in claim 1, which is characterized in that described to obtain the interest point name segment and match point of interest
Commercial circle attribute, comprising:
Matched by the interest point name segment and extract location information in point of interest, and the location information extracted is converted to
Property index value;
The commercial circle attribute is obtained according to the index relative between property index value and commercial circle attribute.
4. method as claimed in claim 3, which is characterized in that the index according between property index value and commercial circle attribute
Before relationship obtains the commercial circle attribute, the method also includes:
Region unit division is carried out to the affiliated zoning of the point of interest of storage according to specified region unit parameter, to divide obtained region unit
Configuration attribute index value;
Commercial circle attribute configuration is carried out to the region unit according to the point of interest in region unit;
Construct the index relative between property index value and commercial circle attribute.
5. such as the described in any item methods of Claims 1-4, which is characterized in that described according to described in commercial circle attribute progress
After the classification of information, which comprises
Client is received to request by the information recommendation that user's Geographic mapping is initiated;
Property index value is converted to according to the location information in information recommendation request;
The commercial circle attribute that there is index relative with the property index value is obtained, Xiang Suoshu client push information category is is obtained
Obtain the information of commercial circle attribute.
6. such as the described in any item methods of Claims 1-4, which is characterized in that the method also includes:
When it is unidentified to the interest point name segment when, confirm information source belonging to the information;
The information is sorted out according to the zoning attribute in the information source, is pushed away with providing the information of user place zoning
It recommends.
7. method as claimed in claim 6, which is characterized in that it is described by the information according to the zoning category in the information source
Property sorted out, before the information recommendation to provide zoning where user, the method also includes:
Commercial circle attribute or zoning attribute when according to the information categorization carry out zoning distribution statistics to the information source, obtain
To the zoning attribute in the information source.
8. a kind of information recommendation method characterized by comprising
Client carries out user's Geographic mapping, obtains location information;
Information recommendation request is initiated to server-side according to the positional information;
Receive the information of commercial circle attribute push of the server-side according to commercial circle where indicating user, the commercial circle attribute and institute
Stating the property index value that location information is converted to has index relative, and the information is in the server-side according to the commercial circle
Attribute is sorted out.
9. a kind of information recommending apparatus characterized by comprising
Data obtaining module obtains information for server-side;
Information identification module, the interest point name for carrying to the information identifies, obtains interest point name segment;
Matching retrieval module is obtained for carrying out matching retrieval in the point of interest of storage according to the interest point name segment
The point of interest that title and the interest point name segment match;
Attribute obtains module, matches the commercial circle attribute of point of interest for obtaining the interest point name segment;
First information classifying module is mentioned for carrying out the classification of the information according to the commercial circle attribute by the information of classification
For the information recommendation of commercial circle where user.
10. a kind of information recommending apparatus characterized by comprising
Initiation module is positioned, user's Geographic mapping is carried out for client, obtains location information;
Initiation module is requested, for initiating information recommendation request to server-side according to the positional information;
Information receiving module, for receiving the letter of commercial circle attribute push of the server-side according to commercial circle where indicating user
The property index value that breath, the commercial circle attribute and the location information are converted to has index relative, and the information is described
Sorted out in server-side according to the commercial circle attribute.
11. a kind of information recommending apparatus characterized by comprising
Processor;And
Memory is stored with computer-readable instruction on the memory, and the computer-readable instruction is held by the processor
Such as information recommendation method described in any item of the claim 1 to 8 is realized when row.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Such as information recommendation method described in any item of the claim 1 to 8 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711243040.9A CN110020150B (en) | 2017-11-30 | 2017-11-30 | Information recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711243040.9A CN110020150B (en) | 2017-11-30 | 2017-11-30 | Information recommendation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110020150A true CN110020150A (en) | 2019-07-16 |
CN110020150B CN110020150B (en) | 2022-10-14 |
Family
ID=67186853
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711243040.9A Active CN110020150B (en) | 2017-11-30 | 2017-11-30 | Information recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110020150B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111369284A (en) * | 2020-03-03 | 2020-07-03 | 浙江网商银行股份有限公司 | Target object type determination method and device |
CN111814077A (en) * | 2020-06-30 | 2020-10-23 | 北京百度网讯科技有限公司 | Information point query method, device, equipment and medium |
WO2023221661A1 (en) * | 2022-05-19 | 2023-11-23 | 北京沃东天骏信息技术有限公司 | Generation method and apparatus for user preferred item information, and electronic device and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100076968A1 (en) * | 2008-05-27 | 2010-03-25 | Boyns Mark R | Method and apparatus for aggregating and presenting data associated with geographic locations |
CN102147795A (en) * | 2010-02-05 | 2011-08-10 | 北京四维图新科技股份有限公司 | Method and device for searching points of interest as well as navigation system |
CN103164512A (en) * | 2013-02-25 | 2013-06-19 | 百度在线网络技术(北京)有限公司 | Processing method and equipment of address information of interest point |
CN103500217A (en) * | 2013-10-09 | 2014-01-08 | 北京火信网络科技有限公司 | Method and system for providing service of identification of region of interest |
-
2017
- 2017-11-30 CN CN201711243040.9A patent/CN110020150B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100076968A1 (en) * | 2008-05-27 | 2010-03-25 | Boyns Mark R | Method and apparatus for aggregating and presenting data associated with geographic locations |
CN102147795A (en) * | 2010-02-05 | 2011-08-10 | 北京四维图新科技股份有限公司 | Method and device for searching points of interest as well as navigation system |
CN103164512A (en) * | 2013-02-25 | 2013-06-19 | 百度在线网络技术(北京)有限公司 | Processing method and equipment of address information of interest point |
CN103500217A (en) * | 2013-10-09 | 2014-01-08 | 北京火信网络科技有限公司 | Method and system for providing service of identification of region of interest |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111369284A (en) * | 2020-03-03 | 2020-07-03 | 浙江网商银行股份有限公司 | Target object type determination method and device |
CN111369284B (en) * | 2020-03-03 | 2023-08-15 | 浙江网商银行股份有限公司 | Target object type determining method and device |
CN111814077A (en) * | 2020-06-30 | 2020-10-23 | 北京百度网讯科技有限公司 | Information point query method, device, equipment and medium |
CN111814077B (en) * | 2020-06-30 | 2024-04-05 | 北京百度网讯科技有限公司 | Information point query method, device, equipment and medium |
WO2023221661A1 (en) * | 2022-05-19 | 2023-11-23 | 北京沃东天骏信息技术有限公司 | Generation method and apparatus for user preferred item information, and electronic device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN110020150B (en) | 2022-10-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105701254B (en) | Information processing method and device for information processing | |
US20150281382A1 (en) | Group creating and joining method, client, server , and system | |
WO2017181613A1 (en) | Search response method, device and system | |
CN105488135B (en) | Live content classification method and device | |
CN105069737A (en) | Mobile service terminal, mobile service system and data processing method for airport services | |
CN103797479B (en) | Method and apparatus for hybrid social search model | |
CN109564571A (en) | Utilize the inquiry recommended method and system of search context | |
CN105917359A (en) | Mobile video search | |
TWI703862B (en) | Content recommendation method and device | |
CN110209810B (en) | Similar text recognition method and device | |
CN104079640B (en) | A kind of user service provides method and system | |
CN109039671A (en) | Group message display methods, device, terminal and storage medium | |
WO2016026432A1 (en) | Business card information query method and cloud server | |
JP2021520531A (en) | Synchronization of access control between computing devices | |
CN106446100A (en) | Content recommendation method and device | |
CN110164415A (en) | A kind of recommended method based on speech recognition, device and medium | |
US10115391B2 (en) | Method and apparatus for providing voice feedback information to user in call | |
CN103902535A (en) | Method, device and system for obtaining associational word | |
WO2020082831A1 (en) | Face-based identity recognition method and apparatus, and electronic device | |
CN109002338A (en) | Page rendering, page finishing information processing method and device | |
CN105743771B (en) | A kind of method, apparatus and electronic equipment of share photos | |
CN110020150A (en) | Information recommendation method and device | |
CN104750718B (en) | The searching method and equipment of a kind of data information | |
CN110889036A (en) | Multi-dimensional information processing method and device and terminal equipment | |
CN108768824A (en) | Information processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |